A method for selecting a detail for a surroundings detection by a sensor based on sensor data. The surroundings are detected by at least one additional sensor, and an object recognition is carried out based on the ascertained sensor data of the at least one additional sensor. Pieces of position information from at least one recognized object are transformed into a coordinate system of the sensor, based on the object recognition, and based on the transformed pieces of position information, the sensor uses a detail of a scanning area for the surroundings detection, or an image detail from already detected sensor data, for an evaluation. A control device is also described.
Legal claims defining the scope of protection. Each claim is shown in both the original legal language and a plain English translation.
2. The method as recited in claim 1, wherein the sensor uses at least one image detail from the already detected sensor data for the evaluation, based on transformed pieces of position information from multiple additional sensors.
The invention relates to sensor-based systems for evaluating environmental or operational conditions using image data and positional information from multiple sensors. The problem addressed is improving the accuracy and reliability of sensor evaluations by leveraging additional contextual data from other sensors, particularly when the primary sensor's data alone may be insufficient or ambiguous. The method involves using a sensor to detect initial data, such as images or other measurements, and then enhancing the evaluation process by incorporating image details from this detected data. To refine the analysis, the system utilizes transformed positional information from multiple additional sensors. These additional sensors provide supplementary data that helps contextualize or correct the primary sensor's readings. The transformation of positional information ensures that the data from different sensors is aligned and compatible for joint evaluation. This approach improves the system's ability to interpret complex environments or conditions by combining spatial and visual information from diverse sources. The method is particularly useful in applications like autonomous navigation, environmental monitoring, or industrial automation, where multiple sensor inputs must be integrated for accurate decision-making.
3. The method as recited in claim 1, wherein the transformation of the pieces of position information is carried out by a central control unit or by a sensor control unit.
This invention relates to a system for processing position information from multiple sensors, particularly in applications where precise spatial data is required, such as robotics, autonomous navigation, or industrial automation. The problem addressed is the need to accurately transform and synchronize position data from different sensors to ensure consistency and reliability in real-time applications. The method involves collecting position information from multiple sensors, each providing data in their own reference frames. The transformation of these pieces of position information is performed by either a central control unit or by individual sensor control units. The central control unit consolidates and processes the data from all sensors, ensuring that the position information is accurately transformed into a common reference frame. Alternatively, each sensor control unit may independently transform its own position data into the common reference frame before transmitting it to the central system. This decentralized approach reduces the computational load on the central unit and improves system scalability. The transformation process accounts for spatial relationships, such as offsets or rotations between sensor reference frames and the common reference frame, ensuring that the combined position data is coherent and usable for navigation, mapping, or control purposes. The invention enhances the accuracy and reliability of multi-sensor positioning systems by providing flexible transformation mechanisms.
4. The method as recited in claim 1, wherein the transformation of the pieces of position information is carried out by the additional sensor, direct communication links being established between the sensor and the additional sensor.
This invention relates to a system for transforming position information in a sensor network, addressing the challenge of accurately processing and relaying spatial data between sensors. The system includes a primary sensor that collects position information from multiple sources and an additional sensor that transforms this data. The transformation process involves direct communication links between the primary sensor and the additional sensor, ensuring real-time data transfer without intermediaries. The additional sensor processes the position information to enhance accuracy, reduce latency, or convert it into a different format suitable for further analysis or transmission. The direct communication links eliminate the need for centralized processing, improving efficiency and reliability in distributed sensor networks. This approach is particularly useful in applications requiring precise spatial data, such as autonomous navigation, environmental monitoring, or industrial automation, where timely and accurate position information is critical. The system ensures seamless integration of multiple sensors while maintaining data integrity and minimizing delays.
5. The method as recited in claim 1, wherein the pieces of position information of the at least one object, provided by the at least one sensor, are changed over time for tracking the at least one object.
This invention relates to object tracking systems that use sensor data to monitor the position of one or more objects over time. The problem addressed is the need for accurate and dynamic tracking of objects as their positions change, which is critical in applications such as surveillance, autonomous navigation, and industrial automation. The system includes at least one sensor that detects and provides position information for one or more objects. The sensor may be a camera, radar, lidar, or other positioning device. The position data is continuously updated to reflect changes in the object's location, enabling real-time tracking. The system processes this time-varying position information to determine the object's movement patterns, velocity, and trajectory. Additional sensors may be used to enhance accuracy or provide redundant data. The method involves collecting position data from the sensor, analyzing the data to detect changes in the object's position over time, and updating the tracking information accordingly. This allows the system to maintain an accurate representation of the object's movement, even as it moves dynamically. The system may also include filtering or predictive algorithms to improve tracking reliability in noisy or uncertain environments. The invention is particularly useful in scenarios where objects move unpredictably or where high precision is required, such as in robotics, vehicle tracking, or security monitoring. By dynamically adjusting to position changes, the system ensures continuous and reliable tracking performance.
6. The method as recited in claim 5, wherein a temporally variable adaptation of the pieces of position information of the at least one object is continued outside a scanning area of the at least one additional sensor.
This invention relates to object tracking systems that use multiple sensors to monitor the position of objects over time. The problem addressed is maintaining accurate tracking of objects when they move outside the scanning area of one or more sensors, which can lead to gaps in position data and reduced tracking reliability. The system involves at least one primary sensor and at least one additional sensor, each capable of detecting and providing position information for one or more objects. The primary sensor continuously tracks the object's position within its scanning area. When the object moves outside this area, the additional sensor takes over tracking. The invention includes a method for adapting the position information of the object in a temporally variable manner, meaning the tracking parameters (such as update frequency, accuracy thresholds, or prediction models) are dynamically adjusted based on factors like object speed, direction, or environmental conditions. The key innovation is that this adaptive tracking continues even when the object is outside the scanning area of the additional sensor. This ensures seamless tracking without interruptions, improving reliability in applications like autonomous navigation, surveillance, or industrial automation. The system may also incorporate predictive algorithms to estimate the object's position when direct sensor data is unavailable, further enhancing continuity. The adaptive mechanism allows the system to balance between computational efficiency and tracking precision, depending on real-time conditions.
7. The method as recited in claim 1, wherein the at least one image detail of the detected sensor data of the sensor that is used for the evaluation is selected based on additional sensor data of a position sensor and data of a map.
A method for evaluating sensor data in autonomous vehicle navigation involves selecting specific image details from sensor data based on additional sensor data from a position sensor and map data. The system uses sensor data, such as camera or LiDAR data, to detect objects or environmental features relevant to navigation. To improve accuracy, the method selects particular image details from this sensor data by cross-referencing the position sensor data, which provides the vehicle's location, with map data, which contains information about the surrounding environment. This selection process ensures that only the most relevant sensor data details are used for evaluation, enhancing the system's ability to make precise navigation decisions. The method may involve filtering or prioritizing sensor data based on the vehicle's position relative to mapped features, such as lane markings, road signs, or obstacles. By integrating position and map data, the system improves the reliability of sensor-based navigation in dynamic environments. This approach reduces processing overhead by focusing on critical sensor details, leading to more efficient and accurate autonomous driving.
8. The method as recited in claim 1, wherein the at least one image detail of the detected sensor data of the sensor that is used for the evaluation is selected based on position data of at least one road user, the position data of the at least one road user being transmitted via a direct or indirect communication link.
This invention relates to a method for evaluating sensor data in a road traffic monitoring system. The method addresses the challenge of accurately detecting and analyzing road users, such as vehicles or pedestrians, by dynamically selecting relevant image details from sensor data based on real-time position data. The position data of road users is transmitted via direct or indirect communication links, such as vehicle-to-vehicle (V2V) or vehicle-to-infrastructure (V2I) networks. By incorporating this position data, the system can prioritize specific regions of the sensor data for evaluation, improving detection accuracy and reducing processing overhead. The method involves capturing sensor data, such as images or radar signals, and then filtering or enhancing the data based on the received position information. This ensures that the evaluation focuses on the most relevant areas, enhancing situational awareness for traffic management or autonomous driving applications. The approach optimizes resource usage by avoiding unnecessary processing of irrelevant data, while maintaining high accuracy in road user detection.
9. The method as recited in claim 1, wherein the at least one image detail of the detected sensor data of the sensor is selected by an artificial intelligence.
This invention relates to sensor data processing, specifically improving the accuracy and efficiency of analyzing sensor data by selectively focusing on relevant image details using artificial intelligence. The problem addressed is the challenge of efficiently extracting meaningful information from sensor data, which often contains a large volume of irrelevant or redundant details that can obscure critical features. Traditional methods may rely on manual selection or fixed algorithms, which lack adaptability to varying conditions or contexts. The invention involves a method where an artificial intelligence system automatically selects at least one image detail from the detected sensor data. The AI evaluates the sensor data to identify and prioritize the most relevant or informative details, enhancing the accuracy of subsequent analysis. This selection process is dynamic, allowing the system to adapt to different environments or scenarios without manual intervention. The AI may use machine learning techniques, such as convolutional neural networks, to recognize patterns or features of interest in the sensor data. By focusing only on the selected details, the method reduces computational overhead and improves processing speed while maintaining or improving analytical performance. This approach is particularly useful in applications like autonomous vehicles, industrial automation, or medical imaging, where real-time or high-precision analysis is critical. The AI-driven selection ensures that the system remains robust and scalable across diverse use cases.
10. The method as recited in claim 1, wherein the evaluation carried out by the sensor is used for a plausibility check of the object recognition of the at least one additional sensor.
This invention relates to sensor-based object recognition systems, particularly for improving reliability in autonomous vehicles or robotic systems. The problem addressed is ensuring accurate object detection by cross-verifying data from multiple sensors, such as cameras, lidar, or radar, to prevent false positives or negatives in dynamic environments. The method involves using a primary sensor to detect and recognize objects in the environment. At least one additional sensor is also used to gather data about the same objects. A secondary sensor, distinct from the primary and additional sensors, performs an independent evaluation of the detected objects. This evaluation is then used to validate or cross-check the object recognition results from the additional sensor(s). The plausibility check helps confirm whether the detected objects are real or potential false detections, enhancing system reliability. The secondary sensor may use different detection principles (e.g., thermal imaging, ultrasonic sensing) to provide a complementary perspective. The method ensures that object recognition is robust against environmental noise, sensor failures, or adversarial conditions, improving safety in applications like autonomous driving or industrial automation.
11. The method as recited in claim 10, wherein the plausibility check is carried out via a request from at least one sensor.
A system and method for verifying the plausibility of sensor data in automotive or industrial applications. The invention addresses the problem of ensuring accurate and reliable sensor readings in environments where sensor data may be corrupted, noisy, or inconsistent. The method involves performing a plausibility check on sensor data to determine whether the data is valid and trustworthy before using it for further processing or control decisions. The plausibility check is triggered by a request from at least one sensor, which may include environmental sensors, motion sensors, or other types of sensors used in automotive or industrial systems. The system may compare the sensor data against predefined thresholds, historical data, or data from other sensors to assess its plausibility. If the data is deemed implausible, the system may flag it for further review, discard it, or trigger corrective actions. The method ensures that only reliable sensor data is used, improving the accuracy and safety of automated systems. The invention may be applied in autonomous vehicles, industrial automation, or other fields where sensor data integrity is critical.
12. The method as recited in claim 1, wherein selection of the object from the image data of the sensor takes place by analyzing only the relevant image detail from a sensor scan.
This invention relates to object selection in sensor-based imaging systems, particularly for improving efficiency in analyzing sensor data. The problem addressed is the computational overhead and inefficiency of processing entire sensor scans when only a specific object or region of interest is needed. Traditional methods often analyze full image data, wasting resources on irrelevant details. The invention provides a method for selecting an object from sensor image data by focusing analysis only on the relevant image detail from a sensor scan. This involves identifying and isolating the specific portion of the sensor data that contains the object of interest, rather than processing the entire scan. The method reduces computational load and improves processing speed by avoiding unnecessary analysis of irrelevant areas. The object selection is performed dynamically, adapting to the sensor's field of view and the object's position within it. This approach is particularly useful in applications like autonomous navigation, industrial inspection, or medical imaging, where real-time processing and resource efficiency are critical. The invention ensures that only the necessary data is analyzed, optimizing system performance without compromising accuracy.
14. The control unit as recited in claim 13, wherein selection of the object from the image data of the sensor takes place by analyzing only the relevant image detail from a sensor scan.
This invention relates to a control unit for processing image data from a sensor, particularly in systems where objects must be identified and selected from sensor scans. The problem addressed is the computational inefficiency of analyzing entire sensor images when only specific regions of interest contain relevant data. The control unit includes a processing module that extracts and analyzes only the relevant image detail from the sensor scan, rather than processing the full image. This selective analysis reduces processing time and resource usage while maintaining accuracy in object detection. The control unit may also include a memory for storing reference data and a communication interface for transmitting processed results. The object selection process involves comparing the relevant image detail against stored reference data to identify and select the object. This approach is particularly useful in applications like autonomous navigation, quality inspection, or surveillance, where real-time processing of sensor data is critical. By focusing only on the relevant portions of the sensor scan, the system achieves faster and more efficient object detection without sacrificing performance.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
September 4, 2019
May 21, 2024
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.